© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2562
    Prev
    Next
    INDEX
    Explanations

    family or dynasty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GIN
    -0.10
    ç½¹
    -0.09
    æĬ½
    -0.09
    .zone
    -0.09
    èıĬèĬ±
    -0.09
    åłµ
    -0.08
    å·¥ä½ľç»ıéªĮ
    -0.08
    ÙħÙĪا
    -0.08
    çİ°åľº
    -0.08
     zone
    -0.08
    POSITIVE LOGITS
    ä¸ĸ代
    0.11
    ä¸ī代
    0.10
    å§ĵ
    0.09
    è¡ĢèĦī
    0.09
    家æĹı
    0.09
     Ø¢ÙĦ
    0.09
     Alf
    0.08
    ä¸ĭä¸Ģ代
    0.08
    ä¸Ģ缴éĥ½
    0.08
    æľĢåĪĿçļĦ
    0.08
    Activations Density 0.129%

    No Known Activations